# amem MCP server

> Provides local, private memory for coding agents to persist facts, skills, and tasks across sessions.

- Repository: https://github.com/sslugic/amem
- Page: https://hostedmcp.org/servers/sslugic/amem
- Transport: stdio
- Stars: 0
- License: MIT
- Latest version: 0.7.5

## Install

### Claude Code

```sh
claude mcp add amem -- npx -y @iamem/amem
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "amem": {
      "command": "npx",
      "args": [
        "-y",
        "@iamem/amem"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "amem": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@iamem/amem"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"amem","type":"stdio","command":"npx","args":["-y","@iamem/amem"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "amem": {
      "command": "npx",
      "args": [
        "-y",
        "@iamem/amem"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add amem -- npx -y @iamem/amem
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.amem]
command = "npx"
args = ["-y", "@iamem/amem"]
```

### Gemini CLI

```sh
gemini mcp add -s user amem npx -- -y @iamem/amem
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "amem": {
      "command": "npx",
      "args": [
        "-y",
        "@iamem/amem"
      ]
    }
  }
}
```

## Tools (16)

- `amem_context`: Retrieve compact local amem memory for a query. Use before exploring files or calling a remote LLM with a large prompt. Pass workspace for named app memory, not only git repos.
- `amem_recipe`: Return the generic amem remember contract: when to call amem_context vs amem_remember. Use if you are unsure whether to read or write memory. Same recipe for every MCP host. Takes no arguments.
- `amem_remember`: Store a durable local fact in amem (stays on this machine). Use kind `private` (or anchor `private`) for personal, non-work facts so they never appear in work repositories' context. When the fact replaces an older one (a newer status, a fixed bug, a changed decision), pass the old claim ids in `supersedes` so the outdated memory stops being served. The response lists `possiblySupersedes`: older look-alikes to retire with amem_supersede if they are now wrong.
- `amem_supersede`: Retire outdated claims so they stop appearing in context: marks them superseded (kept for history, not served). Pass `by` with the claim id that replaces them, if any.
- `amem_repos`: List what amem is monitoring. Each item has kind git or workspace. Workspaces also have a stable slug (MCP id); the display name can differ. Use when asked which projects, workspaces, or repos amem knows about. All arguments are optional.
- `amem_stats`: Usage and savings stats (local lookup time, estimated tokens/ms saved, hit rate) for one workspace/repo or everything. Use when asked how much amem helped, how often it hit, or usage over time. All arguments are optional.
- `amem_graph`: Dump stored facts for a workspace or git repo: claims, components, flows, and recent activity. Use when asked what amem remembers about a project. Prefer amem_context for a ranked packet for the current question. All arguments are optional.
- `amem_status`: Binding, policy, and counts for one workspace/repo, plus the full monitored inventory. Omit workspace for a machine-wide overview. All arguments are optional.
- `amem_skill_list`: List stored skills (procedures the agent learned) as an index of names and descriptions only. Cheap — call this first, then amem_skill_view to load the one you need. Skills are longer procedures; use amem_context for small durable facts. All arguments are optional.
- `amem_skill_view`: Load the full body of one skill by name, or a supporting file inside it. Call this only after amem_skill_list (or the 'Relevant skills' section of an amem context packet) shows a skill worth following.
- `amem_skill_save`: Save a non-trivial multi-step procedure you just worked out as a reusable skill. Use after solving something worth repeating — a workflow, a dead end you found the way past, or a correction the user gave you. Provide a full SKILL.md in `content`, or a description plus body.
- `amem_task_list`: List deferred agent tasks (Kanban) for a workspace/repo. Use for work to do later — not durable facts (use amem_remember for those). Default excludes done tasks. All arguments are optional.
- `amem_task_add`: Create a deferred agent task on the project Kanban (default backlog). Use for work that should not get lost in chat. Durable facts still go through amem_remember.
- `amem_task_update`: Change an existing Kanban task: move it between columns (set status to doing when you start it, blocked when it waits on someone), rename it, or replace its notes or file anchors. Only the fields you pass change. Use amem_task_complete to finish a task and amem_task_add for new work. Returns the updated task as JSON; an unknown id returns an error.
- `amem_task_complete`: Mark a Kanban task done as soon as its work is finished and verified, so the next session does not pick it up again. Records the completion time and keeps the task in history (amem_task_list with include_done shows it). Same as amem_task_update with status done. Returns the completed task as JSON; an unknown id returns an error.
- `amem_usage_report`: Report what you actually did with the last amem context packet, so its savings estimate becomes a measurement instead of a guess. Call this once after you have finished acting on a packet. Do NOT estimate tokens — just list which of the anchors amem gave you you ended up opening anyway (anchors_opened), and whether the packet answered the question without further exploration (answered). amem computes the saving from the real size of the files you did not have to open. Reporting that you opened everything is a useful and expected answer.

## FAQ

### Where is my data stored?

All data is stored locally on your machine in a single SQLite file located in ~/.amem.

### Does my memory leave my machine?

No, the memory is private by design and never leaves your machine; there is no cloud sync or cloud embeddings.

### Which AI clients can use amem?

It works with a wide range of clients including Claude Code, Cursor, Claude Desktop, Copilot, Windsurf, Aider, and Zed.

### Can I review or delete what the agent remembers?

Yes, you can use the amem UI dashboard to see what is remembered, review information, or delete facts with one click.
